This work has been accepted to IEEE Robotics and Automation Letters (RA-L 2025). illustrates a real-world scenario where the double-sided mapping issue arises, presenting examples of both erroneous ...

Both authors contributed equally. Corresponding author. We present Lotus, a diffusion-based visual foundation model for dense geometry prediction. With minimal training data, Lotus achieves SoTA ...

Abstract: The combination of deep learning, artist-curated scans, and Implicit Functions (IF), is enabling the creation of detailed, clothed, 3D humans from images. However, existing methods are far ...